16 files changed, 190 insertions, 45 deletions

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 10e78d00a0bb..2d46862e7bef 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -487,6 +487,16 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
 
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
+#endif
+
 void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
                              void *kaddr, unsigned long len);
+
 #endif
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index dc662fca9230..4111592f0130 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -17,6 +17,7 @@ struct dev_archdata {
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
         struct dma_iommu_mapping        *mapping;
 #endif
+        bool dma_coherent;
 };
 
 struct omap_device;
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 85738b200023..e6e3446abdf6 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -123,11 +123,18 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 
 static inline int set_arch_dma_coherent_ops(struct device *dev)
 {
+        dev->archdata.dma_coherent = true;
         set_dma_ops(dev, &arm_coherent_dma_ops);
         return 0;
 }
 #define set_arch_dma_coherent_ops(dev)  set_arch_dma_coherent_ops(dev)
 
+/* do not use this function in a driver */
+static inline bool is_device_dma_coherent(struct device *dev)
+{
+        return dev->archdata.dma_coherent;
+}
+
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
         unsigned int offset = paddr & ~PAGE_MASK;
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 74124b0d0d79..0415eae1df27 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -2,27 +2,24 @@
 #define _ASM_FIXMAP_H
 
 #define FIXADDR_START           0xffc00000UL
-#define FIXADDR_TOP             0xffe00000UL
-#define FIXADDR_SIZE            (FIXADDR_TOP - FIXADDR_START)
+#define FIXADDR_END             0xfff00000UL
+#define FIXADDR_TOP             (FIXADDR_END - PAGE_SIZE)
 
-#define FIX_KMAP_NR_PTES        (FIXADDR_SIZE >> PAGE_SHIFT)
+#include <asm/kmap_types.h>
 
-#define __fix_to_virt(x)        (FIXADDR_START + ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)        (((x) - FIXADDR_START) >> PAGE_SHIFT)
+enum fixed_addresses {
+        FIX_KMAP_BEGIN,
+        FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
 
-extern void __this_fixmap_does_not_exist(void);
+        /* Support writing RO kernel text via kprobes, jump labels, etc. */
+        FIX_TEXT_POKE0,
+        FIX_TEXT_POKE1,
 
-static inline unsigned long fix_to_virt(const unsigned int idx)
-{
-        if (idx >= FIX_KMAP_NR_PTES)
-                __this_fixmap_does_not_exist();
-        return __fix_to_virt(idx);
-}
+        __end_of_fixed_addresses
+};
 
-static inline unsigned int virt_to_fix(const unsigned long vaddr)
-{
-        BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-        return __virt_to_fix(vaddr);
-}
+void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
+
+#include <asm-generic/fixmap.h>
 
 #endif
diff --git a/arch/arm/include/asm/hw_irq.h b/arch/arm/include/asm/hw_irq.h
index a71b417b1856..af79da40af2a 100644
--- a/arch/arm/include/asm/hw_irq.h
+++ b/arch/arm/include/asm/hw_irq.h
@@ -8,6 +8,7 @@ static inline void ack_bad_irq(int irq)
 {
         extern unsigned long irq_err_count;
         irq_err_count++;
+        pr_crit("unexpected IRQ trap at vector %02x\n", irq);
 }
 
 void set_irq_flags(unsigned int irq, unsigned int flags);
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index d428e386c88e..3446f6a1d9fa 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -219,6 +219,23 @@ void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
 bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
 int __mcpm_cluster_state(unsigned int cluster);
 
+/**
+ * mcpm_sync_init - Initialize the cluster synchronization support
+ *
+ * @power_up_setup: platform specific function invoked during very
+ *                  early CPU/cluster bringup stage.
+ *
+ * This prepares memory used by vlocks and the MCPM state machine used
+ * across CPUs that may have their caches active or inactive. Must be
+ * called only after a successful call to mcpm_platform_register().
+ *
+ * The power_up_setup argument is a pointer to assembly code called when
+ * the MMU and caches are still disabled during boot  and no stack space is
+ * available. The affinity level passed to that code corresponds to the
+ * resource that needs to be initialized (e.g. 1 for cluster level, 0 for
+ * CPU level).  Proper exclusion mechanisms are already activated at that
+ * point.
+ */
 int __init mcpm_sync_init(
         void (*power_up_setup)(unsigned int affinity_level));
 
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index 209e6504922e..a89b4076cde4 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -30,14 +30,14 @@ static inline void set_my_cpu_offset(unsigned long off)
 static inline unsigned long __my_cpu_offset(void)
 {
         unsigned long off;
-        register unsigned long *sp asm ("sp");
 
         /*
          * Read TPIDRPRW.
          * We want to allow caching the value, so avoid using volatile and
          * instead use a fake stack read to hazard against barrier().
          */
-        asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off) : "Q" (*sp));
+        asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off)
+                : "Q" (*(const unsigned long *)current_stack_pointer));
 
         return off;
 }
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 78a779361682..19cfab526d13 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -157,7 +157,15 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 static inline void
 pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 {
-        __pmd_populate(pmdp, page_to_phys(ptep), _PAGE_USER_TABLE);
+        extern pmdval_t user_pmd_table;
+        pmdval_t prot;
+
+        if (__LINUX_ARM_ARCH__ >= 6 && !IS_ENABLED(CONFIG_ARM_LPAE))
+                prot = user_pmd_table;
+        else
+                prot = _PAGE_USER_TABLE;
+
+        __pmd_populate(pmdp, page_to_phys(ptep), prot);
 }
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5cfba15cb401..5e68278e953e 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -20,12 +20,14 @@
 #define PMD_TYPE_FAULT          (_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE          (_AT(pmdval_t, 1) << 0)
 #define PMD_TYPE_SECT           (_AT(pmdval_t, 2) << 0)
+#define PMD_PXNTABLE            (_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4                (_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)           (_AT(pmdval_t, (x)) << 5)
 #define PMD_PROTECTION          (_AT(pmdval_t, 1) << 9)         /* v5 */
 /*
  *   - section
  */
+#define PMD_SECT_PXN    (_AT(pmdval_t, 1) << 0)     /* v7 */
 #define PMD_SECT_BUFFERABLE     (_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE      (_AT(pmdval_t, 1) << 3)
 #define PMD_SECT_XN             (_AT(pmdval_t, 1) << 4)         /* v6 */
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index 9fd61c72a33a..f8f1cff62065 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -76,6 +76,7 @@
 #define PTE_EXT_SHARED          (_AT(pteval_t, 3) << 8)         /* SH[1:0], inner shareable */
 #define PTE_EXT_AF              (_AT(pteval_t, 1) << 10)        /* Access Flag */
 #define PTE_EXT_NG              (_AT(pteval_t, 1) << 11)        /* nG */
+#define PTE_EXT_PXN             (_AT(pteval_t, 1) << 53)        /* PXN */
 #define PTE_EXT_XN              (_AT(pteval_t, 1) << 54)        /* XN */
 
 /*
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 3b30062975b2..d5cac545ba33 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -252,17 +252,57 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
         set_pte_ext(ptep, pteval, ext);
 }
 
-#define PTE_BIT_FUNC(fn,op) \
-static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
-
-PTE_BIT_FUNC(wrprotect, |= L_PTE_RDONLY);
-PTE_BIT_FUNC(mkwrite,   &= ~L_PTE_RDONLY);
-PTE_BIT_FUNC(mkclean,   &= ~L_PTE_DIRTY);
-PTE_BIT_FUNC(mkdirty,   |= L_PTE_DIRTY);
-PTE_BIT_FUNC(mkold,     &= ~L_PTE_YOUNG);
-PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
-PTE_BIT_FUNC(mkexec,   &= ~L_PTE_XN);
-PTE_BIT_FUNC(mknexec,   |= L_PTE_XN);
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
+{
+        pte_val(pte) &= ~pgprot_val(prot);
+        return pte;
+}
+
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
+{
+        pte_val(pte) |= pgprot_val(prot);
+        return pte;
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+        return set_pte_bit(pte, __pgprot(L_PTE_RDONLY));
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+        return clear_pte_bit(pte, __pgprot(L_PTE_RDONLY));
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+        return clear_pte_bit(pte, __pgprot(L_PTE_DIRTY));
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+        return set_pte_bit(pte, __pgprot(L_PTE_DIRTY));
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+        return clear_pte_bit(pte, __pgprot(L_PTE_YOUNG));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+        return set_pte_bit(pte, __pgprot(L_PTE_YOUNG));
+}
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+        return clear_pte_bit(pte, __pgprot(L_PTE_XN));
+}
+
+static inline pte_t pte_mknexec(pte_t pte)
+{
+        return set_pte_bit(pte, __pgprot(L_PTE_XN));
+}
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 601264d983fa..51622ba7c4a6 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -154,9 +154,8 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
         return regs->ARM_sp;
 }
 
-#define current_pt_regs(void) ({                                \
-        register unsigned long sp asm ("sp");                   \
-        (struct pt_regs *)((sp | (THREAD_SIZE - 1)) - 7) - 1;   \
+#define current_pt_regs(void) ({ (struct pt_regs *)                     \
+                ((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1;  \
 })
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index ce73ab635414..d890e41f5520 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -90,14 +90,19 @@ struct thread_info {
 #define init_stack              (init_thread_union.stack)
 
 /*
+ * how to get the current stack pointer in C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+/*
  * how to get the thread information struct from C
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
 static inline struct thread_info *current_thread_info(void)
 {
-        register unsigned long sp asm ("sp");
-        return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+        return (struct thread_info *)
+                (current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 #define thread_saved_pc(tsk)    \
diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h
index f4ab34fd4f72..ee5f3084243c 100644
--- a/arch/arm/include/asm/vfp.h
+++ b/arch/arm/include/asm/vfp.h
@@ -22,6 +22,7 @@
 #define FPSID_NODOUBLE          (1<<20)
 #define FPSID_ARCH_BIT          (16)
 #define FPSID_ARCH_MASK         (0xF  << FPSID_ARCH_BIT)
+#define FPSID_CPUID_ARCH_MASK   (0x7F  << FPSID_ARCH_BIT)
 #define FPSID_PART_BIT          (8)
 #define FPSID_PART_MASK         (0xFF << FPSID_PART_BIT)
 #define FPSID_VARIANT_BIT       (4)
@@ -75,6 +76,10 @@
 /* MVFR0 bits */
 #define MVFR0_A_SIMD_BIT        (0)
 #define MVFR0_A_SIMD_MASK       (0xf << MVFR0_A_SIMD_BIT)
+#define MVFR0_SP_BIT            (4)
+#define MVFR0_SP_MASK           (0xf << MVFR0_SP_BIT)
+#define MVFR0_DP_BIT            (8)
+#define MVFR0_DP_MASK           (0xf << MVFR0_DP_BIT)
 
 /* Bit patterns for decoding the packaged operation descriptors */
 #define VFPOPDESC_LENGTH_BIT    (9)
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index e8275ea88e88..efd562412850 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -5,6 +5,18 @@
 #include <linux/dma-attrs.h>
 #include <linux/dma-mapping.h>
 
+void __xen_dma_map_page(struct device *hwdev, struct page *page,
+             dma_addr_t dev_addr, unsigned long offset, size_t size,
+             enum dma_data_direction dir, struct dma_attrs *attrs);
+void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+                size_t size, enum dma_data_direction dir,
+                struct dma_attrs *attrs);
+void __xen_dma_sync_single_for_cpu(struct device *hwdev,
+                dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
+void __xen_dma_sync_single_for_device(struct device *hwdev,
+                dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
 static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
                 dma_addr_t *dma_handle, gfp_t flags,
                 struct dma_attrs *attrs)
@@ -20,20 +32,56 @@ static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
 }
 
 static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-             unsigned long offset, size_t size, enum dma_data_direction dir,
-             struct dma_attrs *attrs)
+             dma_addr_t dev_addr, unsigned long offset, size_t size,
+             enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-        __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+        bool local = PFN_DOWN(dev_addr) == page_to_pfn(page);
+        /* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise
+         * is a foreign page grant-mapped in dom0. If the page is local we
+         * can safely call the native dma_ops function, otherwise we call
+         * the xen specific function. */
+        if (local)
+                __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+        else
+                __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
 }
 
-void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir,
-                struct dma_attrs *attrs);
+                struct dma_attrs *attrs)
+{
+        unsigned long pfn = PFN_DOWN(handle);
+        /* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will
+         * always return false. If the page is local we can safely call the
+         * native dma_ops function, otherwise we call the xen specific
+         * function. */
+        if (pfn_valid(pfn)) {
+                if (__generic_dma_ops(hwdev)->unmap_page)
+                        __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+        } else
+                __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
 
-void xen_dma_sync_single_for_cpu(struct device *hwdev,
-                dma_addr_t handle, size_t size, enum dma_data_direction dir);
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+                dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+        unsigned long pfn = PFN_DOWN(handle);
+        if (pfn_valid(pfn)) {
+                if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
+                        __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+        } else
+                __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
 
-void xen_dma_sync_single_for_device(struct device *hwdev,
-                dma_addr_t handle, size_t size, enum dma_data_direction dir);
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+                dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+        unsigned long pfn = PFN_DOWN(handle);
+        if (pfn_valid(pfn)) {
+                if (__generic_dma_ops(hwdev)->sync_single_for_device)
+                        __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+        } else
+                __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
 
 #endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 135c24a5ba26..68c739b3fdf4 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_remap(cookie, size) ioremap_cache((cookie), (size))
 #define xen_unmap(cookie) iounmap((cookie))
 
+bool xen_arch_need_swiotlb(struct device *dev,
+                           unsigned long pfn,
+                           unsigned long mfn);
+
 #endif /* _ASM_ARM_XEN_PAGE_H */